Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.6168. Min Act: -0.1700
Data Index: 2935886 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.3668. Min Act: -0.1700
Data Index: 7693173 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.2731. Min Act: -0.1700
Data Index: 3477217 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.3043. Min Act: -0.1700
Data Index: 2370578 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.3043. Min Act: -0.1700
Data Index: 3815739 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.2731. Min Act: -0.1700
Data Index: 5363099 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.2106. Min Act: -0.1700
Data Index: 4143504 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.2106. Min Act: -0.1700
Data Index: 8088104 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.1793. Min Act: -0.1700
Data Index: 2311634 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.1793. Min Act: -0.1700
Data Index: 8249636 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.1481. Min Act: -0.1700
Data Index: 365994 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0856. Min Act: -0.1700
Data Index: 6909251 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0856. Min Act: -0.1700
Data Index: 2957611 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.1168. Min Act: -0.1700
Data Index: 7130769 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.1168. Min Act: -0.1700
Data Index: 289661 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0856. Min Act: -0.1700
Data Index: 224536 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0856. Min Act: -0.1700
Data Index: 3129298 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0856. Min Act: -0.1700
Data Index: 8789138 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0543. Min Act: -0.1700
Data Index: 2414560 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6168. Min Range: -6.6168
Max Act: 6.0543. Min Act: -0.1700
Data Index: 306820 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19